A Novel Multi-Task Learning Framework for Semi-Supervised Semantic Parsing
Lists
Only you see this
Abstract
While sequence-to-sequence (seq2seq) models on semantic parsing have demonstrated significant performance, the need for large amounts of labeled data still hinders the application of this technology to resource-poor domains. In this work, we work on alleviating data scarcity in semantic parsing. We propose a semi-supervised semantic parsing methods by exploiting unlabeled natural utterances in a novel multi-task learning framework. Two strategies are proposed. The first one takes entity sequences as training targets to improve the representations of encoder and reduce entity-mistakes in prediction. The second one extends Mean Teacher to seq2seq model and generates more target-side data to improve the generalizability of decoder network. Experiments demonstrate that our proposed methods significantly outperform the supervised baseline and achieve more impressive improvement than previous methods.
BibTeX
@article{qi2020novel,
author = {Qi Qi and Xiaolu Wang and Haifeng Sun and Jingyu Wang and Xiao Liang and Jianxin Liao},
title = {{A Novel Multi-Task Learning Framework for Semi-Supervised Semantic Parsing}},
journal = {IEEE ACM Trans. Audio Speech Lang. Process.},
year = {2020},
doi = {10.1109/taslp.2020.3018233},
}Loading related content...